DOCSLIB.ORG

Q-Learning in Continuous State and Action Spaces

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Q-Learning in Continuous State and Action Spaces -Learning in Continuous Q State and Action Spaces Chris Gaskett, David Wettergreen, and Alexander Zelinsky Robotic Systems Laboratory Department of Systems Engineering Research School of Information Sciences and Engineering The Australian National University Canberra, ACT 0200 Australia [cg dsw alex]@syseng.anu.edu.au j j Abstract. -learning can be used to learn a control policy that max- imises a scalarQ reward through interaction with the environment. - learning is commonly applied to problems with discrete states and ac-Q tions. We describe a method suitable for control tasks which require con- tinuous actions, in response to continuous states. The system consists of a neural network coupled with a novel interpolator. Simulation results are presented for a non-holonomic control task. Advantage Learning, a variation of -learning, is shown enhance learning speed and reliability for this task.Q 1 Introduction Reinforcement learning systems learn by trial-and-error which actions are most valuable in which situations (states) [1]. Feedback is provided in the form of a scalar reward signal which may be delayed. The reward signal is defined in relation to the task to be achieved; reward is given when the system is successfully achieving the task. The value is updated incrementally with experience and is defined as a discounted sum of expected future reward. The learning systems choice of actions in response to states is called its policy. Reinforcement learning lies between the extremes of supervised learning, where the policy is taught by an expert, and unsupervised learning, where no feedback is given and the task is to find structure in data. There are two prevalent approaches to reinforcement learning: -learning and actor-critic learning. In -learning [2] the expected value of eachQ action in each state is stored. In -learningQ the policy is formed by executing the action with the highest expectedQ value. In actor-critic learning [3] a critic learns the value of each state. The value is the expected reward over time from the environment under the current policy. The actor tries to maximise a local reward signal from the critic by choosing actions close to its current policy then changing its policy depending upon feedback from the critic. In turn, the critic adjusts the value of states in response to rewards received following the actor's policy. The main advantage of -learning over actor-critic learning is exploration insensitivity|the ability toQ learn without necessarily following the current pol- icy. However, actor-critic learning has a major advantage over current imple- mentations of -learning; the ability to respond to smoothly varying states with smoothly varyingQ actions. Actor-critic systems can form a continuous mapping from state to action and update this policy based on the local reward signal from the critic. -learning is generally considered in the case that states and actions are both discrete.Q In some real world situations, and especially in control, it is advantageous to treat both states and actions as continuous variables. This paper describes a continuous state and action -learning method and applies it to a simulated control task. Essential characteristicsQ of a continuous state and action -learning system are also described. Advantage Learning [4] is found to be anQ important variation of -learning for these tasks. Q 2 -Learning Q -learning works by incrementally updating the expected values of actions in states.Q For every possible state, every possible action is assigned a value which is a function of both the immediate reward for taking that action and the expected reward in the future based on the new state that is the result of taking that action. This is expressed by the one-step -update equation, Q (x; u) := (1 α) (x; u) + α (R + γ max (xt+1; ut+1)) ; (1) Q − Q Q where is the expected value of performing action u in state x; x is the state vector;Qu is the action vector; R is the reward; α is a learning rate which controls convergence and γ is the discount factor. The discount factor makes rewards earned earlier more valuable than those received later. This method learns the values of all actions, rather than just finding the optimal policy. This knowledge is expensive in terms of the amount of informa- tion which has to be stored, but it does bring benefits. -learning is exploration insensitive, any action can be carried out at any time andQ information is gained from this experience. Actor-critic learning does not have this ability, actions must follow or nearly follow the current policy. This exploration insensitivity allows -learning to learn from other controllers, even if they are directed to- ward achievingQ a different task they can provide valuable data. Knowledge from several -learners can be combined, as the values of non-optimal actions are known,Q a compromise action can be found. In the standard -learning implementation -values are stored in a table. One cell is requiredQ per combination of state andQ action. This implementation is not amenable to continuous state and action problems. 3 Continuous States and Actions Many real world control problems require actions of a continuous nature, in response to continuous state measurements. It should be possible that actions vary smoothly in response to smooth changes in state. But most learning systems, indeed most classical AI techniques, are designed to operate in discrete domains, manipulating symbols rather than real numbered variables. Some problems that we may wish to address, such as high-performance control of mobile robots, cannot be adequately carried out with coarsely coded inputs and outputs. Motor commands need to vary smoothly and accurately in response to continuous changes in state. -learning with discretised states and actions scale poorly. As the number of stateQ and action variables increase, the size of the table used to store -values grows exponentially. Accurate control requires that variables be quantisedQ finely, but as these systems fail to generalise between similar states and actions, they require large quantities of training data. If the learning task described in Sect. 7 was attempted with a discrete -learning algorithm the number of -values to be stored in the table wouldQ be extremely large. For example, discretisedQ roughly to seven levels, the eight state variables and two action variables would require almost 300 million elements. Without generalisation, producing this num- ber of experiences is impractical. Using a coarser representation of states leads to aliasing, functionally different situations map to the same state and are thus indistinguishable. It is possible to avoid these discretisation problems entirely by using learning methods which can deal directly with continuous states and actions. 4 Continuous State and Action -Learning Q There have been several recent attempts at extending the -learning framework to continuous state and action spaces [5, 6, 7, 8, 9]. Q We believe that there are eight criteria that are necessary and sufficient for a system to be capable of this type of learning. Listed in in Fig. 1, these require- ments are a combination of those required for basic -learning as described in Sect. 2 combined with the type of continuous behaviourQ described in Sect. 3. None of the -learning systems discussed below appear to fulfil all of these cri- teria completely.Q In particular, many systems cannot learn a policy where actions vary smoothly with smooth changes in state (criteria Continuity). In these not- quite continuous systems a small change in state cannot cause a small change in action. In effect the function which maps state to action is a staircase|a piecewise constant function. Sections 4.1{4.6 describe various real valued state and action -learning methods and techniques and rate them (in an unfair and biased manner)Q against the criteria in Fig. 1. 4.1 Adaptive Critic Methods Werbos's adaptive critic family of methods [5] use several feedforward artificial neural networks to implement reinforcement learning. The adaptive critic family includes methods closely related to actor-critic and -learning. A learnt dynamic model assists in assigning reward to components of theQ action vector (not meeting Action Selection: Finds action with the highest expected value quickly. State Evaluation: Finds value of a state quickly as required for the - update equation (1). A state's value is the value of highestQ valued action in that state. Evaluation: Stores or approximates the entire -function as required Q for the -update equation (1). Q Model-Free: RequiresQ no model of system dynamics to be known or learnt. Flexible Policy: Allows representation of a broad range of policies to allow freedom in developing a novel controller. Continuity: Actions can vary smoothly with smooth changes in state. State Generalisation: Generalises between similar states, reducing the amount of exploration required in state space. Action Generalisation: Generalises between similar actions, reducing the amount of exploration required in action space. Fig. 1. Essential capabilities for a continuous state and action -learning system Q the Model-Free criteria). If the dynamic model is already known, or learning one is easier than learning the controller itself, model based adaptive critic methods are an efficient approach to continuous state, continuous action reinforcement learning. 4.2 CMAC Based -learning Q Santamaria, Ashwin and Sutton [6] have presented results for -learning sys- tems using Albus's CMAC (Cerebellar Model Articulation Controller)Q [10]. The CMAC is a function approximation system which features spatial locality, avoid- ing the unlearning problem described in Sect. 6. It is a compromise between a look up table and a weight-based approximator. It can generalise between simi- lar states, but it involves discretisation, making it impossible to completely fulfil the Continuity criteria. In [6] the inputs to the CMAC are the state and action, the output is the expected value.
Load more

Recommended publications
  • Backpropagation and Deep Learning in the Brain
    Backpropagation and Deep Learning in the Brain Simons Institute -- Computational Theories of the Brain 2018 Timothy Lillicrap DeepMind, UCL With: Sergey Bartunov, Adam Santoro, Jordan Guerguiev, Blake Richards, Luke Marris, Daniel Cownden, Colin Akerman, Douglas Tweed, Geoffrey Hinton The “credit assignment” problem The solution in artificial networks: backprop Credit assignment by backprop works well in practice and shows up in virtually all of the state-of-the-art supervised, unsupervised, and reinforcement learning algorithms. Why Isn’t Backprop “Biologically Plausible”? Why Isn’t Backprop “Biologically Plausible”? Neuroscience Evidence for Backprop in the Brain? A spectrum of credit assignment algorithms: A spectrum of credit assignment algorithms: A spectrum of credit assignment algorithms: How to convince a neuroscientist that the cortex is learning via [something like] backprop - To convince a machine learning researcher, an appeal to variance in gradient estimates might be enough. - But this is rarely enough to convince a neuroscientist. - So what lines of argument help? How to convince a neuroscientist that the cortex is learning via [something like] backprop - What do I mean by “something like backprop”?: - That learning is achieved across multiple layers by sending information from neurons closer to the output back to “earlier” layers to help compute their synaptic updates. How to convince a neuroscientist that the cortex is learning via [something like] backprop 1. Feedback connections in cortex are ubiquitous and modify the
    [Show full text]
  • Self-Discriminative Learning for Unsupervised Document Embedding
    Self-Discriminative Learning for Unsupervised Document Embedding Hong-You Chen∗1, Chin-Hua Hu∗1, Leila Wehbe2, Shou-De Lin1 1Department of Computer Science and Information Engineering, National Taiwan University 2Machine Learning Department, Carnegie Mellon University fb03902128, [email protected], [email protected], [email protected] Abstract ingful a document embedding as they do not con- sider inter-document relationships. Unsupervised document representation learn- Traditional document representation models ing is an important task providing pre-trained such as Bag-of-words (BoW) and TF-IDF show features for NLP applications. Unlike most competitive performance in some tasks (Wang and previous work which learn the embedding based on self-prediction of the surface of text, Manning, 2012). However, these models treat we explicitly exploit the inter-document infor- words as flat tokens which may neglect other use- mation and directly model the relations of doc- ful information such as word order and semantic uments in embedding space with a discrimi- distance. This in turn can limit the models effec- native network and a novel objective. Exten- tiveness on more complex tasks that require deeper sive experiments on both small and large pub- level of understanding. Further, BoW models suf- lic datasets show the competitiveness of the fer from high dimensionality and sparsity. This is proposed method. In evaluations on standard document classification, our model has errors likely to prevent them from being used as input that are relatively 5 to 13% lower than state-of- features for downstream NLP tasks. the-art unsupervised embedding models. The Continuous vector representations for docu- reduction in error is even more pronounced in ments are being developed.
    [Show full text]
  • Training Autoencoders by Alternating Minimization
    Under review as a conference paper at ICLR 2018 TRAINING AUTOENCODERS BY ALTERNATING MINI- MIZATION Anonymous authors Paper under double-blind review ABSTRACT We present DANTE, a novel method for training neural networks, in particular autoencoders, using the alternating minimization principle. DANTE provides a distinct perspective in lieu of traditional gradient-based backpropagation techniques commonly used to train deep networks. It utilizes an adaptation of quasi-convex optimization techniques to cast autoencoder training as a bi-quasi-convex optimiza- tion problem. We show that for autoencoder configurations with both differentiable (e.g. sigmoid) and non-differentiable (e.g. ReLU) activation functions, we can perform the alternations very effectively. DANTE effortlessly extends to networks with multiple hidden layers and varying network configurations. In experiments on standard datasets, autoencoders trained using the proposed method were found to be very promising and competitive to traditional backpropagation techniques, both in terms of quality of solution, as well as training speed. 1 INTRODUCTION For much of the recent march of deep learning, gradient-based backpropagation methods, e.g. Stochastic Gradient Descent (SGD) and its variants, have been the mainstay of practitioners. The use of these methods, especially on vast amounts of data, has led to unprecedented progress in several areas of artificial intelligence. On one hand, the intense focus on these techniques has led to an intimate understanding of hardware requirements and code optimizations needed to execute these routines on large datasets in a scalable manner. Today, myriad off-the-shelf and highly optimized packages exist that can churn reasonably large datasets on GPU architectures with relatively mild human involvement and little bootstrap effort.
    [Show full text]
  • Double Backpropagation for Training Autoencoders Against Adversarial Attack
    1 Double Backpropagation for Training Autoencoders against Adversarial Attack Chengjin Sun, Sizhe Chen, and Xiaolin Huang, Senior Member, IEEE Abstract—Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data storage and transmission, however, the current autoencoders are easily attacked, i.e., one can slightly modify an input but has totally different codes. The vulnerability is rooted the sensitivity of the autoencoders and to enhance the robustness, we propose to adopt double backpropagation (DBP) to secure autoencoder such as VAE and DRAW. We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack. After smoothing the gradient by DBP, we further smooth the label by Gaussian Mixture Model (GMM), aiming for accurate and robust classification. We demonstrate in MNIST, CelebA, SVHN that our method leads to a robust autoencoder resistant to attack and a robust classifier able for image transition and immune to adversarial attack if combined with GMM. Index Terms—double backpropagation, autoencoder, network robustness, GMM. F 1 INTRODUCTION N the past few years, deep neural networks have been feature [9], [10], [11], [12], [13], or network structure [3], [14], I greatly developed and successfully used in a vast of fields, [15]. such as pattern recognition, intelligent robots, automatic Adversarial attack and its defense are revolving around a control, medicine [1]. Despite the great success, researchers small ∆x and a big resulting difference between f(x + ∆x) have found the vulnerability of deep neural networks to and f(x).
    [Show full text]
  • Reinforcement Learning Data Science Africa 2018 Abuja, Nigeria (12 Nov - 16 Nov 2018)
    Reinforcement Learning Data Science Africa 2018 Abuja, Nigeria (12 Nov - 16 Nov 2018) Chika Yinka-Banjo, PhD Ayorkor Korsah, PhD University of Lagos Ashesi University Nigeria Ghana Outline • Introduction to Machine learning • Reinforcement learning definitions • Example reinforcement learning problems • The Markov decision process • The optimal policy • Value function & Q-value function • Bellman Equation • Q-learning • Building a simple Q-learning agent (coding) • Recap • Where to go from here? Introduction to Machine learning • Artificial Intelligence (AI) is the study and design of Intelligent agents. • An Intelligent agent can perceive its environment through sensors and it can act on its environment through actuators. • E.g. Agent: Humanoid robot • Environment: Earth? • Sensors: Camera, tactile sensor etc. • Actuators: Motors, grippers etc. • Machine learning is a subfield of Artificial Intelligence Branches of AI Introduction to Machine learning • Machine learning techniques learn from data without being explicitly programmed to do so. • Machine learning models enable the agent to learn from its own experience by extracting useful information from feedback from its environment. • Three types of learning feedback: • Supervised learning • Unsupervised learning • Reinforcement learning Branches of Machine learning Supervised learning • Supervised learning: the machine learning model is trained on many labelled examples of input-output pairs. • Such that when presented with a novel input, the model can estimate accurately what the correct output should be. • Data(x, y): x is input data, y is label Supervised learning task in the form of classification • Goal: learn a function to map x -> y • Examples include; Classification, regression object detection, image captioning etc. Unsupervised learning • Unsupervised learning: here the model extract useful information from unlabeled and unstructured data.
    [Show full text]
  • Unsupervised Speech Representation Learning Using Wavenet Autoencoders Jan Chorowski, Ron J
    1 Unsupervised speech representation learning using WaveNet autoencoders Jan Chorowski, Ron J. Weiss, Samy Bengio, Aaron¨ van den Oord Abstract—We consider the task of unsupervised extraction speaker gender and identity, from phonetic content, properties of meaningful latent representations of speech by applying which are consistent with internal representations learned autoencoding neural networks to speech waveforms. The goal by speech recognizers [13], [14]. Such representations are is to learn a representation able to capture high level semantic content from the signal, e.g. phoneme identities, while being desired in several tasks, such as low resource automatic speech invariant to confounding low level details in the signal such as recognition (ASR), where only a small amount of labeled the underlying pitch contour or background noise. Since the training data is available. In such scenario, limited amounts learned representation is tuned to contain only phonetic content, of data may be sufficient to learn an acoustic model on the we resort to using a high capacity WaveNet decoder to infer representation discovered without supervision, but insufficient information discarded by the encoder from previous samples. Moreover, the behavior of autoencoder models depends on the to learn the acoustic model and a data representation in a fully kind of constraint that is applied to the latent representation. supervised manner [15], [16]. We compare three variants: a simple dimensionality reduction We focus on representations learned with autoencoders bottleneck, a Gaussian Variational Autoencoder (VAE), and a applied to raw waveforms and spectrogram features and discrete Vector Quantized VAE (VQ-VAE). We analyze the quality investigate the quality of learned representations on LibriSpeech of learned representations in terms of speaker independence, the ability to predict phonetic content, and the ability to accurately re- [17].
    [Show full text]
  • A Review of Unsupervised Artificial Neural Networks with Applications
    A REVIEW OF UNSUPERVISED ARTIFICIAL NEURAL NETWORKS WITH APPLICATIONS Samson Damilola Fabiyi Department of Electronic and Electrical Engineering, University of Strathclyde 204 George Street, G1 1XW, Glasgow, United Kingdom [email protected] ABSTRACT designer) who uses his or her knowledge of the environment to Artificial Neural Networks (ANNs) are models formulated to train the network with labelled data sets [7]. Hence, the mimic the learning capability of human brains. Learning in artificial neural networks learn by receiving input and target ANNs can be categorized into supervised, reinforcement and pairs of several observations from the labelled data sets, unsupervised learning. Application of supervised ANNs is processing the input, comparing the output with the target, limited to when the supervisor’s knowledge of the environment computing the error between the output and target, and using is sufficient to supply the networks with labelled datasets. the error signal and the concept of backward propagation to Application of unsupervised ANNs becomes imperative in adjust the weights interconnecting the network’s neurons with situations where it is very difficult to get labelled datasets. This the aim of minimising the error and optimising performance [6, paper presents the various methods, and applications of 7]. Fine-tuning of the network continues until the set of weights unsupervised ANNs. In order to achieve this, several secondary that minimise the discrepancy between the output and the sources of information, including academic journals and desired output is obtained. Figure 1 shows the block diagram conference proceedings, were selected. Autoencoders, self- which conceptualizes supervised learning in ANNs.
    [Show full text]
  • Approaching Hanabi with Q-Learning and Evolutionary Algorithm
    St. Cloud State University theRepository at St. Cloud State Culminating Projects in Computer Science and Department of Computer Science and Information Technology Information Technology 12-2020 Approaching Hanabi with Q-Learning and Evolutionary Algorithm Joseph Palmersten [email protected] Follow this and additional works at: https://repository.stcloudstate.edu/csit_etds Part of the Computer Sciences Commons Recommended Citation Palmersten, Joseph, "Approaching Hanabi with Q-Learning and Evolutionary Algorithm" (2020). Culminating Projects in Computer Science and Information Technology. 34. https://repository.stcloudstate.edu/csit_etds/34 This Starred Paper is brought to you for free and open access by the Department of Computer Science and Information Technology at theRepository at St. Cloud State. It has been accepted for inclusion in Culminating Projects in Computer Science and Information Technology by an authorized administrator of theRepository at St. Cloud State. For more information, please contact [email protected]. Approaching Hanabi with Q-Learning and Evolutionary Algorithm by Joseph A Palmersten A Starred Paper Submitted to the Graduate Faculty of St. Cloud State University In Partial Fulfillment of the Requirements for the Degree of Master of Science in Computer Science December, 2020 Starred Paper Committee: Bryant Julstrom, Chairperson Donald Hamnes Jie Meichsner 2 Abstract Hanabi is a cooperative card game with hidden information that requires cooperation and communication between the players. For a machine learning agent to be successful at the Hanabi, it will have to learn how to communicate and infer information from the communication of other players. To approach the problem of Hanabi the machine learning methods of Q- learning and Evolutionary algorithm are proposed as potential solutions.
    [Show full text]
  • Linear Prediction-Based Wavenet Speech Synthesis
    LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis Min-Jae Hwang Frank Soong Eunwoo Song Search Solution Microsoft Naver Corporation Seongnam, South Korea Beijing, China Seongnam, South Korea [email protected] [email protected] [email protected] Xi Wang Hyeonjoo Kang Hong-Goo Kang Microsoft Yonsei University Yonsei University Beijing, China Seoul, South Korea Seoul, South Korea [email protected] [email protected] [email protected] Abstract—We propose a linear prediction (LP)-based wave- than the speech signal, the training and generation processes form generation method via WaveNet vocoding framework. A become more efficient. WaveNet-based neural vocoder has significantly improved the However, the synthesized speech is likely to be unnatural quality of parametric text-to-speech (TTS) systems. However, it is challenging to effectively train the neural vocoder when the target when the prediction errors in estimating the excitation are database contains massive amount of acoustical information propagated through the LP synthesis process. As the effect such as prosody, style or expressiveness. As a solution, the of LP synthesis is not considered in the training process, the approaches that only generate the vocal source component by synthesis output is vulnerable to the variation of LP synthesis a neural vocoder have been proposed. However, they tend to filter. generate synthetic noise because the vocal source component is independently handled without considering the entire speech To alleviate this problem, we propose an LP-WaveNet, production process; where it is inevitable to come up with a which enables to jointly train the complicated interactions mismatch between vocal source and vocal tract filter.
    [Show full text]
  • Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning
    Lecture 11 Recurrent Neural Networks I CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago May 01, 2017 Lecture 11 Recurrent Neural Networks I CMSC 35246 Introduction Sequence Learning with Neural Networks Lecture 11 Recurrent Neural Networks I CMSC 35246 Some Sequence Tasks Figure credit: Andrej Karpathy Lecture 11 Recurrent Neural Networks I CMSC 35246 MLPs only accept an input of fixed dimensionality and map it to an output of fixed dimensionality Great e.g.: Inputs - Images, Output - Categories Bad e.g.: Inputs - Text in one language, Output - Text in another language MLPs treat every example independently. How is this problematic? Need to re-learn the rules of language from scratch each time Another example: Classify events after a fixed number of frames in a movie Need to resuse knowledge about the previous events to help in classifying the current. Problems with MLPs for Sequence Tasks The "API" is too limited. Lecture 11 Recurrent Neural Networks I CMSC 35246 Great e.g.: Inputs - Images, Output - Categories Bad e.g.: Inputs - Text in one language, Output - Text in another language MLPs treat every example independently. How is this problematic? Need to re-learn the rules of language from scratch each time Another example: Classify events after a fixed number of frames in a movie Need to resuse knowledge about the previous events to help in classifying the current. Problems with MLPs for Sequence Tasks The "API" is too limited. MLPs only accept an input of fixed dimensionality and map it to an output of fixed dimensionality Lecture 11 Recurrent Neural Networks I CMSC 35246 Bad e.g.: Inputs - Text in one language, Output - Text in another language MLPs treat every example independently.
    [Show full text]
  • Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting
    water Article Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting Halit Apaydin 1 , Hajar Feizi 2 , Mohammad Taghi Sattari 1,2,* , Muslume Sevba Colak 1 , Shahaboddin Shamshirband 3,4,* and Kwok-Wing Chau 5 1 Department of Agricultural Engineering, Faculty of Agriculture, Ankara University, Ankara 06110, Turkey; [email protected] (H.A.); [email protected] (M.S.C.) 2 Department of Water Engineering, Agriculture Faculty, University of Tabriz, Tabriz 51666, Iran; [email protected] 3 Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam 4 Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam 5 Department of Civil and Environmental Engineering, Hong Kong Polytechnic University, Hong Kong, China; [email protected] * Correspondence: [email protected] or [email protected] (M.T.S.); [email protected] (S.S.) Received: 1 April 2020; Accepted: 21 May 2020; Published: 24 May 2020 Abstract: Due to the stochastic nature and complexity of flow, as well as the existence of hydrological uncertainties, predicting streamflow in dam reservoirs, especially in semi-arid and arid areas, is essential for the optimal and timely use of surface water resources. In this research, daily streamflow to the Ermenek hydroelectric dam reservoir located in Turkey is simulated using deep recurrent neural network (RNN) architectures, including bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), long short-term memory (LSTM), and simple recurrent neural networks (simple RNN). For this purpose, daily observational flow data are used during the period 2012–2018, and all models are coded in Python software programming language.
    [Show full text]
  • A Hybrid Model Consisting of Supervised and Unsupervised Learning for Landslide Susceptibility Mapping
    remote sensing Article A Hybrid Model Consisting of Supervised and Unsupervised Learning for Landslide Susceptibility Mapping Zhu Liang 1, Changming Wang 1,* , Zhijie Duan 2, Hailiang Liu 1, Xiaoyang Liu 1 and Kaleem Ullah Jan Khan 1 1 College of Construction Engineering, Jilin University, Changchun 130012, China; [email protected] (Z.L.); [email protected] (H.L.); [email protected] (X.L.); [email protected] (K.U.J.K.) 2 State Key Laboratory of Hydroscience and Engineering Tsinghua University, Beijing 100084, China; [email protected] * Correspondence: [email protected]; Tel.: +86-135-0441-8751 Abstract: Landslides cause huge damage to social economy and human beings every year. Landslide susceptibility mapping (LSM) occupies an important position in land use and risk management. This study is to investigate a hybrid model which makes full use of the advantage of supervised learning model (SLM) and unsupervised learning model (ULM). Firstly, ten continuous variables were used to develop a ULM which consisted of factor analysis (FA) and k-means cluster for a preliminary landslide susceptibility map. Secondly, 351 landslides with “1” label were collected and the same number of non-landslide samples with “0” label were selected from the very low susceptibility area in the preliminary map, constituting a new priori condition for a SLM, and thirteen factors were used for the modeling of gradient boosting decision tree (GBDT) which represented for SLM. Finally, the performance of different models was verified using related indexes. The results showed that the performance of the pretreated GBDT model was improved with sensitivity, specificity, accuracy Citation: Liang, Z.; Wang, C.; Duan, and the area under the curve (AUC) values of 88.60%, 92.59%, 90.60% and 0.976, respectively.
    [Show full text]